STANDARD ERRORS PRESENTATION AND DISEMINATION AT THE STATISTICAL OFFICE OF THE REPUBLIC OF SLOVENIA Rudi Seljak Statistical Office of the Republic of Slovenia.

Slides:



Advertisements
Similar presentations
Constructing Confidence Intervals based on Register Statistics Thomas Laitila Statistics Sweden and Örebro university Presentation.
Advertisements

1 Virtual COMSATS Inferential Statistics Lecture-7 Ossam Chohan Assistant Professor CIIT Abbottabad.
Chapter 10: Estimating with Confidence
Enhancing Data Quality of Distributive Trade Statistics Workshop for African countries on the Implementation of International Recommendations for Distributive.
Small Area Estimates of Fuel Poverty in Scotland Phil Clarke (ONS), Ganka Mueller (Scottish Government)
NLSCY – Suggestions for papers. Objectives of the Presentation zEmphasize proper ways to use the NLSCY data zIdentify the key factors we are looking at.
Chapter 8 Estimation: Additional Topics
Chapter 11: Sequential Clinical Trials Descriptive Exploratory Experimental Describe Find Cause Populations Relationships and Effect Sequential Clinical.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 7-1 Chapter 7 Confidence Interval Estimation Statistics for Managers.
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Basic Business Statistics 10 th Edition.
Business Statistics: A Decision-Making Approach, 6e © 2005 Prentice-Hall, Inc. Chap 7-1 Introduction to Statistics: Chapter 8 Estimation.
Chap 9-1 Statistics for Business and Economics, 6e © 2007 Pearson Education, Inc. Chapter 9 Estimation: Additional Topics Statistics for Business and Economics.
Copyright © 2010 Pearson Education, Inc. Publishing as Prentice Hall Statistics for Business and Economics 7 th Edition Chapter 9 Hypothesis Testing: Single.
8-1 Copyright ©2011 Pearson Education, Inc. publishing as Prentice Hall Chapter 8 Confidence Interval Estimation Statistics for Managers using Microsoft.
Copyright ©2011 Pearson Education 8-1 Chapter 8 Confidence Interval Estimation Statistics for Managers using Microsoft Excel 6 th Global Edition.
Chapter 8 Introduction to Hypothesis Testing
Copyright © 2013 Pearson Education, Inc. Publishing as Prentice Hall Statistics for Business and Economics 8 th Edition Chapter 9 Hypothesis Testing: Single.
Business Statistics, A First Course (4e) © 2006 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Business Statistics, A First Course.
Statistics for Managers Using Microsoft Excel, 4e © 2004 Prentice-Hall, Inc. Chap 7-1 Chapter 7 Confidence Interval Estimation Statistics for Managers.
Metadata driven application for aggregation and tabular protection Andreja Smukavec SURS.
ICVS IN SLOVENIA Tatjana Škrbec. Content of presentation  Short history  Crime victim survey 2001 within SORS  Methodology and content of questionnaire.
Business Statistics: A Decision-Making Approach, 6e © 2005 Prentice-Hall, Inc. Chap 7-1 Business Statistics: A Decision-Making Approach 6 th Edition Chapter.
Confidence Interval Estimation
Correlation.
Rudi Seljak, Metka Zaletel Statistical Office of the Republic of Slovenia TAX DATA AS A MEANS FOR THE ESSENTIAL REDUCTION OF THE SHORT-TERM SURVEYS RESPONSE.
1 The system aspect of statistical quality Q2014 european conference on quality in official statistics Special session: Consistency of Concepts and Applied.
Virtual COMSATS Inferential Statistics Lecture-6
Basic Business Statistics, 11e © 2009 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Basic Business Statistics 11 th Edition.
Confidence Interval Estimation
Chap 8-1 Copyright ©2013 Pearson Education, Inc. publishing as Prentice Hall Chapter 8 Confidence Interval Estimation Business Statistics: A First Course.
© 2003 Prentice-Hall, Inc.Chap 6-1 Business Statistics: A First Course (3 rd Edition) Chapter 6 Sampling Distributions and Confidence Interval Estimation.
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc. Chap 8-1 Chapter 8 Confidence Interval Estimation Basic Business Statistics 11 th Edition.
Chap 20-1 Statistics for Business and Economics, 6e © 2007 Pearson Education, Inc. Chapter 20 Sampling: Additional Topics in Sampling Statistics for Business.
16-1 Copyright  2010 McGraw-Hill Australia Pty Ltd PowerPoint slides to accompany Croucher, Introductory Mathematics and Statistics, 5e Chapter 16 The.
Estimation Bias, Standard Error and Sampling Distribution Estimation Bias, Standard Error and Sampling Distribution Topic 9.
© 2003 Prentice-Hall, Inc.Chap 7-1 Basic Business Statistics (9 th Edition) Chapter 7 Sampling Distributions.
The Scientific Method Formulation of an H ypothesis P lanning an experiment to objectively test the hypothesis Careful observation and collection of D.
Statistics for Managers Using Microsoft Excel, 5e © 2008 Pearson Prentice-Hall, Inc.Chap 8-1 Statistics for Managers Using Microsoft® Excel 5th Edition.
1 Things That May Affect Estimates from the American Community Survey.
Quality Reporting at SORS – Experiences and Future Perspectives Rudi Seljak, Tina Ostrež Statistical Office of the Republic of Slovenia.
Populations, Samples, & Data Summary in Nat. Resource Mgt. ESRM 304.
Data Quality & dissemination D. Sahoo Dy. Director General Central Statistical Organization, India.
Metadata driven application for data processing – from local toward global solution Rudi Seljak Statistical Office of the Republic of Slovenia.
Some ACS Data Issues and Statistical Significance (MOEs) Table Release Rules Statistical Filtering & Collapsing Disclosure Review Board Statistical Significance.
Basic Concepts of Correlation. Definition A correlation exists between two variables when the values of one are somehow associated with the values of.
Sampling Error Estimation – SORS practice Rudi Seljak, Petra Blažič Statistical Office of the Republic of Slovenia.
Things that May Affect the Estimates from the American Community Survey Updated February 2013.
Chap 7-1 Basic Business Statistics (10 th Edition) Chapter 7 Sampling Distributions.
Sampling Distributions. Sampling Distribution Is the Theoretical probability distribution of a sample statistic Is the Theoretical probability distribution.
Chap 7-1 A Course In Business Statistics, 4th © 2006 Prentice-Hall, Inc. A Course In Business Statistics 4 th Edition Chapter 7 Estimating Population Values.
Basic Business Statistics, 10e © 2006 Prentice-Hall, Inc. Chap 8-1 Confidence Interval Estimation.
Chapter Thirteen Copyright © 2004 John Wiley & Sons, Inc. Sample Size Determination.
© Copyright McGraw-Hill 2000
European Conference on Quality in Official Statistics 8-11 July 2008 Mr. Hing-Wang Fung Census and Statistics Department Hong Kong, China (
Chapter 8 : Estimation.
1 C. ARRIBAS, D. LORCA, A. SALINERO & A. COLMENERO Measuring statistical quality at the Spanish National Statistical Institute.
Chap 7-1 A Course In Business Statistics, 4th © 2006 Prentice-Hall, Inc. A Course In Business Statistics 4 th Edition Chapter 7 Estimating Population Values.
The Application for Statistical Processing at SURS Andreja Smukavec, SURS Rudi Seljak, SURS UNECE Statistical Data Confidentiality Work Session Helsinki,
Statistics for Managers Using Microsoft Excel, 5e © 2008 Pearson Prentice-Hall, Inc.Chap 8-1 Statistics for Managers Using Microsoft® Excel 5th Edition.
SAMPLE SIZE.
RECENT DEVELOPMENT OF SORS METADATA REPOSITORIES FOR FASTER AND MORE TRANSPARENT PRODUCTION PROCESS Work Session on Statistical Metadata 9-11 February.
QUALITY ASSESSMENT OF THE REGISTER-BASED SLOVENIAN CENSUS 2011 Rudi Seljak, Apolonija Flander Oblak Statistical Office of the Republic of Slovenia.
Confidence Intervals for a Population Proportion Excel.
Copyright © 2013 Pearson Education, Inc. Publishing as Prentice Hall Statistics for Business and Economics 8 th Edition Chapter 9 Hypothesis Testing: Single.
Dr.N.K.Tyagi, SAMPLE SIZE The average in the form of estimate ‘p’ or mean should be of known along with its precision and tolerable error,
Chapter 8 Confidence Interval Estimation Statistics For Managers 5 th Edition.
Basic Business Statistics (8th Edition)
Rudi Seljak, Aleš Krajnc
ESTIMATION
Tomaž Špeh, Rudi Seljak Statistical Office of the Republic of Slovenia
Presentation transcript:

STANDARD ERRORS PRESENTATION AND DISEMINATION AT THE STATISTICAL OFFICE OF THE REPUBLIC OF SLOVENIA Rudi Seljak Statistical Office of the Republic of Slovenia

The summary of the presentation Introduction The “old” system for standard error presentation Reasons for the revision The revised system Conclusions

Introduction Sample surveys are still the most commonly used means for the collection of the needed data in the official statistics. Precision of the statistical results is still very important criteria of the quality of the statistical results. It is important obligation of the national statistical institutes to estimate the sampling errors and then to disseminate and represent these errors to the users in the transparent and clearly readable form.

The “old” system at SORS The standard errors for the estimated statistical results were very rarely explicitly published. Estimated coefficients of variation were used to determine degree of precision. The four different degrees of precision were defined: –Estimates with sufficient degree of precision (CV <10%). Value disseminated with no denotation. –Less precise estimates (10% ≤ CV < 15%). Value disseminated in the single bracket. –Imprecise estimates (15% < CV ≤ 30%). Value disseminated in the double bracket. –Extremely imprecise estimates (30% < CV). Value not published but replaced with the sign “. ”.

The “old” system – example (LFS)

Reasons for the revision Using brackets for the denotation signs is not the best solution for the dissemination through the electronic means. Using the denotation of different degrees of precision is not sufficient for the needs of some more demanding users. Definition of the degrees of precision by using only the coefficient of variation is not appropriate for some (non- dimensional) statistics (e.g. proportions).

“CV criteria” problem Applying the direct CV criteria in the case of the non- dimensional statistics could cause the serious inconsistencies. Suppose we want to estimate the proportion of the units with certain characteristic in the large population. Disseminating q=1-p instead

CV- p:q differences

The revised system Standard errors could be disseminated explicitly or by using the denotations for the different degrees of precision. –Denotations for the releases with small amount of the results (e.g. First release) and for the general releases (e.g. Statistical Yearbook). –Explicit dissemination in the case of more exhaustive and domain oriented releases. Three degrees of precision: –The estimate of acceptable precision → published without limitations –Less precise estimates → flagged for caution with letter M –Too imprecise estimates to be published → suppressed for use by letter N

The revised system cont’d For the totals or means of the positive, continuous variables the limits are determined directly on the basis of the coefficient of variation. –CV < 10% → estimate of acceptable precision → published without denotations –CV between 10%-30% → less precise estimate → flagged for caution with letter M –CV>30% → too imprecise estimate to be published → suppressed for use by letter N

Limits for the proportions The “limit standard errors” limits are calculated for the case p=0.5 by using the CV criteria. Then this limits are used for each value of the estimated proportion p

Limits for the proportions cont’d se < 0.05 → estimate of acceptable precision → published without denotations se between 0.05 and 0.15 → less precise estimate → flagged for caution with letter M se>0.15 → too imprecise estimate to be published → suppressed for use by letter N For the number of the units with certain characteristics, the limits are derived from the above limits by using the formula se(N·p)=N ·se(p)

The revised system – example (Tourism Travels of Domestic Population)

Application for standard error calculation To enable standardize and transparent calculation of the standard errors a special sas application was built. The application enables aggregation, standard error calculation and also denotation with the special signs, if needed. The application is designed as a metadata driven system. So far the application enables calculation of standard error for five types of statistics.

Conclusions The system of denotation of different degrees of less precise estimates, based on the coefficient of variation was used at SORS for many years. Some critical exploration pointed out the need for theoretical and technical revision of the system. The main new features of the revised system: –Denotation with signs as well as explicit dissemination of standard errors could be used. –The “bracket signs” are replaced with “letter signs”. – Different criteria for different types of statistics are used. –Metadata driven application which enables standardized process of standard error calculation was built.